Construction method of long-pile wharf pile foundation lateral displacement prediction model

Abstract

The invention relates to the technical field of pile foundation engineering, in particular to a construction method of a long-pile wharf pile foundation lateral displacement prediction model. The method comprises the following steps that displacement, stress and load parameter monitoring is conducted on a pile foundation of the high-pile wharf, and real-time monitoring parameter data is generated; performing working condition identification on the pile foundation structure through the real-time monitoring parameter data to generate working condition data of the pile foundation structure; multi-source load characteristic analysis is conducted on the pile foundation structure working condition data, load coupling effect calculation is conducted, and load action data are generated; performing soil-pile interaction analysis according to the load action data to generate soil-pile response data; and performing material performance deterioration evaluation according to the soil-pile response data to generate material state data. The working condition identification method based on the multi-source monitoring data is established, comprehensive perception of the pile foundation structure state is achieved, and a reliable data basis is provided for subsequent displacement prediction.

Description

Technical Field

[0001] The invention relates to the technical field of pile foundation engineering, and in particular to a method for constructing a lateral displacement prediction model for a high-pile wharf pile foundation. Background Art

[0002] High-pile wharf is a common wharf structure, mainly used in ports, shipping and other fields. Its design and construction process involves many aspects. The piles of high-pile wharf mainly include the following types: concrete piles, steel piles and wooden piles; the design of piles needs to consider the following factors: bearing capacity, settlement control and seismic performance; the construction methods of high-pile wharf piles mainly include: piling method, pouring method and static pressure method. The lateral displacement of the pile foundation of high-pile wharf refers to the displacement of the pile foundation along the horizontal plane under the action of external loads (such as tides, waves, ship collisions, etc.). Lateral displacement is one of the important indicators of pile foundation safety and stability. Especially in hydraulic structures and wharf projects, the control of lateral displacement is crucial to prevent structural damage and ensure the long-term stability of the structure.

[0003] However, the lateral displacement prediction model of high-pile wharf pile foundation often has the following problems: due to the lack of analysis of the coupling effect between loads, it is impossible to fully identify the comprehensive impact of different loads on the lateral displacement of the pile foundation, which easily leads to deviations in the prediction results. Traditional methods often do not consider the impact of changes in environmental factors such as temperature, humidity and corrosion on material properties and pile foundation stability, which affects the degradation assessment of materials and the reliability analysis of pile foundations. Summary of the invention

[0004] Based on this, it is necessary for the present invention to provide a method for constructing a lateral displacement prediction model for a high-pile wharf pile foundation to solve at least one of the above technical problems.

[0005] To achieve the above object, a method for constructing a lateral displacement prediction model for a pile foundation of a high-pile wharf comprises the following steps:

[0006] Step S1: monitor the displacement, stress and load parameters of the pile foundation of the high-pile wharf to generate real-time monitoring parameter data; identify the working condition of the pile foundation structure through the real-time monitoring parameter data to generate the working condition data of the pile foundation structure;

[0007] Step S2: Perform multi-source load characteristic analysis on the pile foundation structure working condition data, and calculate the load coupling effect to generate load action data; perform soil-pile interaction analysis based on the load action data to generate soil-pile response data;

[0008] Step S3: evaluating material performance degradation according to soil-pile response data to generate material status data; analyzing the impact of environmental factors based on temperature, humidity and corrosion according to the material status data to generate environmental impact characteristic data; extracting features from real-time monitoring parameter data, and performing dynamic feature fusion based on correlation analysis on environmental correction data to obtain displacement-environment-load correlation characteristic data;

[0009] Step S4: using the associated feature data to train the deep learning model and obtain the prediction model parameters; performing time series feature analysis on the load action data and the prediction model parameters, and optimizing the prediction accuracy based on the attention mechanism to generate dynamic prediction control data; adaptively updating the prediction model parameters according to the dynamic prediction control data to obtain optimized model parameters;

[0010] Step S5: Continuously predict the lateral displacement of the pile foundation using the optimized model parameters to generate displacement prediction data; quantify the uncertainty and conduct reliability evaluation on the displacement prediction data to generate corrected prediction result data.

[0011] The present invention monitors displacement, stress and load parameters in real time, which helps to quickly identify the structural state of the pile foundation and generate accurate monitoring data. These data can reflect the behavior of the structure under actual working conditions and provide a data basis for subsequent predictions. By using monitoring data to identify working conditions, the structural state can be analyzed and classified in real time to obtain working condition characteristics. This feature provides reliable reference data for subsequent load coupling and soil-pile analysis, and improves the adaptability of the model. Multi-source load feature analysis combined with coupling effect calculation can effectively capture the multiple effects of external loads on pile foundations and provide more accurate load data for soil-pile interaction analysis. Soil-pile interaction analysis can be combined with actual working conditions for refined simulation, and the generated soil-pile response data can accurately describe the response behavior of the structure under complex working conditions. This is very important for the model to capture the synergistic relationship between soil and pile bodies and improve prediction accuracy. Material performance degradation assessment captures the degradation process of structural materials under different loads by analyzing soil-pile response data. This helps to identify potential fatigue damage and support long-term performance prediction. The impact analysis of environmental factors generates environmental impact feature data through the evaluation of temperature, humidity and corrosion, further improving the adaptability of the model in the actual environment. The impact of environmental factors on the structure is dynamically reflected in the feature data, which improves the accuracy and wide applicability of the model prediction. By training the deep learning model with associated feature data, the model can autonomously identify complex relationships in the data and improve the prediction accuracy. Based on the optimization of time series feature analysis and attention mechanism, the sensitivity of the model to future time series changes can be enhanced, and the timeliness and stability of the prediction can be improved. The dynamic prediction control data optimizes the model parameters by adaptively updating, so that the model can quickly adjust when the load and environmental factors change, ensuring the long-term stability and accuracy of the model and reducing the cumulative effect of the prediction error. After optimizing the model parameters, the continuous prediction of the lateral displacement of the pile foundation is carried out, realizing the dynamic evaluation of the displacement behavior. Through uncertainty quantification and reliability evaluation, the uncertain factors in the prediction can be identified and the prediction results can be corrected in time. Correcting the prediction result data makes the error control of the model more accurate in practical applications, improves the prediction reliability and practicality of the model, and enhances the stability and effectiveness of the model in complex working conditions and environments. In general, this method achieves accurate prediction of the lateral displacement of high-pile pier pile foundations through systematic steps and data fusion. It demonstrates significant technical advantages in working condition identification, soil-pile interaction analysis, material degradation, environmental impact, and prediction model optimization, ensuring the practicality and reliability of the method. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0013] Figure 1The figure is a schematic flow chart of the steps of the method for constructing a lateral displacement prediction model for pile foundation of a high-pile wharf according to the present invention;

[0014] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0015] Figure 3 for Figure 1 Detailed step flow chart of step S2 in FIG. DETAILED DESCRIPTION

[0016] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0017] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0018] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0019] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for constructing a lateral displacement prediction model for a pile foundation of a high-pile wharf, the method comprising the following steps:

[0020] Step S1: monitor the displacement, stress and load parameters of the pile foundation of the high-pile wharf to generate real-time monitoring parameter data; identify the working condition of the pile foundation structure through the real-time monitoring parameter data to generate the working condition data of the pile foundation structure;

[0021] In the embodiment of the present invention, a variety of sensors are arranged on the pile foundation to collect displacement, stress and load parameter data in real time, and the data acquisition system is used to continuously record these data to generate real-time monitoring parameter data to reflect the dynamic working condition of the structure. These parameter data are analyzed using a structural working condition identification algorithm (such as a Bayesian classifier) ​​to identify the working condition of the pile foundation structure. Through data processing, the structural conditions of the pile foundation under different load and environmental conditions are classified to generate pile foundation structure working condition data, which provides early warning for scenes with frequent tidal changes or variable sediment composition.

[0022] Step S2: Perform multi-source load characteristic analysis on the pile foundation structure working condition data, and calculate the load coupling effect to generate load action data; perform soil-pile interaction analysis based on the load action data to generate soil-pile response data;

[0023] The embodiment of the present invention performs multi-source load characteristic analysis on the working condition data of the pile foundation structure, including load types such as tidal force, ship impact force and thermal stress. The coupling effect of the load is calculated using finite element analysis (FEM) to obtain load action data, revealing the impact of multiple loads on the pile foundation. Based on the load action data, the improved Mohr-Coulomb model is used to perform soil-pile interaction analysis, and the soil response under each load scenario is calculated to generate soil-pile response data. This process is particularly important for high-pile docks with large water level changes because the load interactions are complex.

[0024] Step S3: evaluating material performance degradation according to soil-pile response data to generate material status data; analyzing the impact of environmental factors based on temperature, humidity and corrosion according to the material status data to generate environmental impact characteristic data; extracting features from real-time monitoring parameter data, and performing dynamic feature fusion based on correlation analysis on environmental correction data to obtain displacement-environment-load correlation characteristic data;

[0025] The embodiment of the present invention uses soil-pile response data to evaluate the degradation of material performance, and simulates the performance of materials that change over time under load and environmental stress through an aging model to generate material status data. The environmental impact factor is calculated in combination with the effects of temperature, humidity and corrosion, and dynamically adjusted through real-time environmental monitoring input. The displacement characteristics of the real-time monitoring data are extracted, and the environmental correction data is fused with the displacement feature data using a feature fusion method based on correlation analysis to generate displacement-environment-load correlation feature data. This process is particularly critical in tropical ports with high humidity, because the rapid degradation of the material will directly affect the stability of the pile foundation.

[0026] Step S4: using the associated feature data to train the deep learning model and obtain the prediction model parameters; performing time series feature analysis on the load action data and the prediction model parameters, and optimizing the prediction accuracy based on the attention mechanism to generate dynamic prediction control data; adaptively updating the prediction model parameters according to the dynamic prediction control data to obtain optimized model parameters;

[0027] The embodiment of the present invention uses the associated feature data to train a deep learning model, such as a long short-term memory (LSTM) network, to capture the time dependency in the data and generate model parameters for predicting the lateral displacement of the pile foundation. The load action data is analyzed for time series characteristics in combination with these model parameters, and the attention mechanism is applied to improve the accuracy of the prediction and generate dynamic prediction control data. The adaptive parameter update algorithm continuously optimizes the model parameters based on the control data, thereby forming optimized model parameters suitable for coping with frequent load change scenarios such as seasonal storms or port traffic flow changes.

[0028] Step S5: Continuously predict the lateral displacement of the pile foundation using the optimized model parameters to generate displacement prediction data; quantify the uncertainty and conduct reliability evaluation on the displacement prediction data to generate corrected prediction result data.

[0029] The embodiment of the present invention uses the optimized model parameters to continuously predict the lateral displacement of the pile foundation and generate displacement prediction data. Monte Carlo simulation is used to quantify uncertainty, evaluate the reliability of the prediction, and calculate confidence intervals for each prediction. The prediction data is evaluated for reliability and corrected prediction result data is generated. This implementation process allows port authorities to evaluate the displacement prediction of pile foundations under complex load and environmental conditions to ensure that the prediction meets the reliability threshold, which is particularly suitable for commercial ports with high load demands and significant environmental changes.

[0030] The present invention monitors displacement, stress and load parameters in real time, which helps to quickly identify the structural state of the pile foundation and generate accurate monitoring data. These data can reflect the behavior of the structure under actual working conditions and provide a data basis for subsequent predictions. By using monitoring data to identify working conditions, the structural state can be analyzed and classified in real time to obtain working condition characteristics. This feature provides reliable reference data for subsequent load coupling and soil-pile analysis, and improves the adaptability of the model. Multi-source load feature analysis combined with coupling effect calculation can effectively capture the multiple effects of external loads on pile foundations and provide more accurate load data for soil-pile interaction analysis. Soil-pile interaction analysis can be combined with actual working conditions for refined simulation, and the generated soil-pile response data can accurately describe the response behavior of the structure under complex working conditions. This is very important for the model to capture the synergistic relationship between soil and pile bodies and improve prediction accuracy. Material performance degradation assessment captures the degradation process of structural materials under different loads by analyzing soil-pile response data. This helps to identify potential fatigue damage and support long-term performance prediction. The impact analysis of environmental factors generates environmental impact feature data through the evaluation of temperature, humidity and corrosion, further improving the adaptability of the model in the actual environment. The impact of environmental factors on the structure is dynamically reflected in the feature data, which improves the accuracy and wide applicability of the model prediction. By training the deep learning model with associated feature data, the model can autonomously identify complex relationships in the data and improve the prediction accuracy. Based on the optimization of time series feature analysis and attention mechanism, the sensitivity of the model to future time series changes can be enhanced, and the timeliness and stability of the prediction can be improved. The dynamic prediction control data optimizes the model parameters by adaptively updating, so that the model can quickly adjust when the load and environmental factors change, ensuring the long-term stability and accuracy of the model and reducing the cumulative effect of the prediction error. After optimizing the model parameters, the continuous prediction of the lateral displacement of the pile foundation is carried out, realizing the dynamic evaluation of the displacement behavior. Through uncertainty quantification and reliability evaluation, the uncertain factors in the prediction can be identified and the prediction results can be corrected in time. Correcting the prediction result data makes the error control of the model more accurate in practical applications, improves the prediction reliability and practicality of the model, and enhances the stability and effectiveness of the model in complex working conditions and environments. In general, this method achieves accurate prediction of the lateral displacement of high-pile pier pile foundations through systematic steps and data fusion. It demonstrates significant technical advantages in working condition identification, soil-pile interaction analysis, material degradation, environmental impact, and prediction model optimization, ensuring the practicality and reliability of the method.

[0031] Preferably, step S1 comprises the following steps:

[0032] Step S11: using multi-source sensors installed on the pile foundation of the high-pile wharf and the soil in the surrounding area to collect sensor parameters in real time, thereby obtaining pile foundation displacement data, pile foundation force data and environmental load data, wherein the multi-source sensors include displacement sensors, stress sensors and load sensors;

[0033] In order to obtain real-time pile foundation displacement, stress and environmental load data, the embodiment of the present invention installs multi-source sensors on the pile foundation of the high-pile wharf and the surrounding soil area, including high-precision displacement sensors, stress sensors and load sensors. The displacement sensors are installed at the top, bottom and middle positions of the pile foundation to capture the displacement at different heights; the stress sensors are installed on the surface of the pile foundation and in the soil to monitor the stress distribution at different depths of the pile foundation; the load sensors are installed in the soil around the pile foundation to evaluate the load changes under the action of the surrounding soil and water. In practical applications, such as in coastal areas, due to the influence of hydrological conditions, the sampling frequency of the sensor needs to be set to 10Hz to capture instantaneous load and displacement changes, ensuring that the data collected by the sensor in real time reflects the dynamic changes of the wharf environment.

[0034] Step S12: pre-processing the pile foundation displacement data, pile foundation force data and environmental load data, and performing unified data dimension processing to obtain real-time monitoring parameter data;

[0035] The pile foundation displacement, force and environmental load data collected by the embodiment of the present invention may have abnormal values ​​or missing values. In order to ensure the accuracy and consistency of the data, the abnormal data is first cleaned and completed, and then the data of different dimensions such as displacement (unit: mm), stress (unit: MPa), load (unit: kN) are unified into dimensionless values ​​using a standardized method. Through normalization or Z-score standardization, all data are within the same range to facilitate subsequent data analysis. For example, for abnormal high-frequency load data generated by a port in a specific season, the 3σ criterion can be used to remove abnormal values, thereby obtaining stable real-time monitoring parameter data for further analysis.

[0036] Step S13: Perform static working condition identification on the real-time monitoring parameter data to obtain static working condition characteristic data, wherein the static working condition identification specifically includes static load working condition classification, structural deformation feature extraction, stress distribution pattern recognition and support condition evaluation;

[0037] The static working condition identification of the embodiment of the present invention is mainly based on the low-frequency part of the monitoring data. First, the data is low-pass filtered to remove the high-frequency dynamic response to ensure that only static features are obtained. Then, the working conditions of the real-time monitoring data are classified to extract the static load response characteristics of the pile foundation under specific loading conditions. Taking the seawall wharf as an example, by comparing the stress distribution of the pile foundation when there is no tidal influence and the wind is stable, the static load characteristics can be identified and the structural deformation analysis can be performed. At the same time, by analyzing the stress distribution pattern, it is possible to identify whether there are abnormal stress conditions in local areas of the wharf pile foundation, and classify the support conditions to ensure the stability of the wharf under normal conditions.

[0038] Step S14: performing dynamic response feature extraction, vibration modal analysis, dynamic load feature identification, and dynamic operating condition identification for structural dynamic characteristic evaluation based on the real-time monitoring parameter data, thereby obtaining dynamic operating condition feature data;

[0039] The embodiment of the present invention is aimed at dynamic working condition identification, and mainly extracts high-frequency dynamic response characteristics. The vibration frequency distribution is obtained through fast Fourier transform (FFT), and the vibration mode of the dock pile foundation is identified. Then, the low-frequency static load signal is removed based on high-pass filtering, and the high-frequency response is retained to analyze the transient load characteristics. In actual operation, for example, in the event of a storm or a ship berthing, the dynamic response characteristics of the pile foundation structure are identified through modal analysis to ensure that it can remain stable under sudden loads. In addition, by analyzing the dynamic load characteristic data, the seismic performance of the dock under different weather conditions can be judged, providing a basis for subsequent disaster prevention design.

[0040] Step S15: Perform information collaborative fusion processing on the static working condition characteristic data and the dynamic working condition characteristic data, so as to obtain the pile foundation structure working condition data.

[0041] The embodiment of the present invention performs information fusion processing on the static working condition characteristic data and the dynamic working condition characteristic data. First, the two types of data are subjected to dimensionality reduction processing through principal component analysis (PCA) to remove redundant information and extract main features. Then, Kalman filtering is used for collaborative processing to obtain more accurate pile foundation structure working condition data. In practical applications, for example, when evaluating the overall wind and wave resistance of coastal docks, the static deformation characteristics and dynamic vibration characteristics are fused to obtain more representative overall structural working condition data of the pile foundation, which can more comprehensively reflect the stability of the dock under various working conditions and provide a basis for subsequent structural safety assessments.

[0042] The present invention uses multi-source sensors (including displacement, stress and load sensors) to collect key parameters of the pile foundation and surrounding soil in real time, ensuring the comprehensiveness of the data. Multi-source sensors can synchronously capture displacement, force and environmental load information, making the acquired data more real and complete, and fully reflecting the state of the pile foundation under actual working conditions. This real-time data acquisition method enhances the timeliness of the data, helps the subsequent working condition identification and predicted dynamic response, and makes the model more sensitive to working condition changes. The data is preprocessed, including steps such as denoising and filling missing data, to ensure the quality of the data and improve the reliability of the data. The unified processing of data dimensions ensures the numerical comparability and consistency of different data sources, making the subsequent working condition identification and feature analysis more accurate. The preprocessed data reflects the real monitoring situation with higher accuracy, provides high-quality basic data for subsequent analysis, and reduces the risk of deviation of the model due to data errors. Static working condition identification extracts characteristic data of the pile foundation under static load, such as static load working condition classification, structural deformation characteristics, stress distribution pattern and support condition evaluation. These static characteristics can reflect the stress state of the pile foundation under stable conditions, and are particularly helpful in understanding the structural performance under long-term load conditions. The extraction of static feature data plays an important role in the parameter setting of the prediction model and the analysis of the long-term stress behavior of the pile foundation, and provides basic state parameters for subsequent working condition analysis. Dynamic working condition identification captures the vibration mode and dynamic load characteristics of the pile foundation under dynamic loads by extracting dynamic features of real-time monitoring parameter data. These dynamic feature data can reflect the response of the structure under vibration and periodic loads, and are important data for dynamic safety assessment and model training of pile foundations. By evaluating the dynamic characteristics of the structure, the safety state of the pile foundation under different dynamic working conditions can be predicted, and a risk prediction reference under dynamic conditions can be provided, so that the model can adapt to complex dynamic working condition changes. Information fusion processing of static and dynamic working condition feature data helps to form comprehensive pile foundation working condition data. The fused working condition data contains the comprehensive characteristics of the structure under static and dynamic loads, and fully reflects the overall stress and deformation of the pile foundation. Collaborative fusion processing enhances the correlation between data, helps to identify the process of working condition conversion, and provides a more accurate working condition reference for subsequent lateral displacement prediction. This data fusion improves the overall adaptability of the prediction model and ensures the accuracy and reliability of the prediction. Overall, this process establishes an efficient multi-source sensor data acquisition, data preprocessing and working condition identification method, and realizes full-process support from data acquisition to working condition feature extraction. Through the collaborative fusion of static and dynamic working condition feature data, the model can fully understand the structural characteristics and stress state of the pile foundation from multiple dimensions, and improve the robustness and adaptability of the prediction model under complex working conditions.

[0043] Preferably, step S13 comprises the following steps:

[0044] Step S131: Classifying the environmental load data in the real-time monitoring parameter data based on the loading mode, loading amplitude and loading sequence, and identifying the load condition according to the preset static load condition classification standard, thereby obtaining static load condition classification data;

[0045] In the classification processing of environmental load data, the embodiment of the present invention first analyzes the loading mode, loading amplitude and loading sequence. For example, for the load data collected during a typhoon, by analyzing the hourly loading amplitude change curve, the increase in wind intensity in a short period of time can be identified, and the typical wind load pattern can be classified. At the same time, according to the preset static load condition classification standard, the loading characteristics with smaller amplitude and stable sequence are classified as static conditions, so as to identify different static load types, such as long-term constant wind pressure or water pressure under the influence of tides, and generate static load condition classification data. This type of data can effectively reflect the load-bearing state of the wharf pile foundation over a long period of time, which is helpful to judge the long-term stability of the structure.

[0046] Step S132: extracting deformation characteristics of the pile foundation displacement data, and calculating characteristic quantities of displacement amplitude, deformation trend, deformation rate and deformation mode, thereby obtaining structural deformation characteristic data;

[0047] In order to extract the deformation characteristics of the pile foundation, the embodiment of the present invention first obtains the maximum and minimum amplitudes from the displacement data to calculate the deformation amplitude, and at the same time, based on time series analysis, obtains the deformation rate and identifies the trend. In a typical application, for example, a pier pile foundation is deformed due to water pressure. The periodic changes of the deformation with the tide can be observed through the daily displacement amplitude records. Then, the acceleration curve is used to analyze the deformation rate to obtain the velocity characteristics of the deformation. At the same time, the deformation mode is identified by the curve fitting method to determine whether the pile foundation is bending upward, displacing horizontally or settling downward, thereby obtaining the structural deformation characteristic data. These data can be directly used for subsequent structural safety assessments to help predict the long-term deformation trend of the pile foundation.

[0048] Step S133: performing stress distribution pattern recognition based on stress distribution law, stress concentration area, stress transfer path and stress level based on the pile foundation stress data, thereby obtaining stress distribution pattern data;

[0049] When the embodiment of the present invention identifies the stress distribution of the pile foundation, it first analyzes the stress concentration area and stress level based on the three-dimensional stress distribution diagram of the pile foundation force data. For example, in the data collected under high wind speed, it can be observed that there is an obvious stress concentration phenomenon near the upper end of the pile foundation, and at the same time, the stress transfer path in the pile body shows a distribution pattern that gradually decays from the top of the pile to the bottom of the pile body. Then, according to the change in stress level, the stress distribution characteristics of key parts are identified and it is determined whether there is a high stress concentration phenomenon. The stress distribution pattern data generated in this way can be used to detect potential structural weak areas and judge the stress bearing capacity of the pile foundation under harsh working conditions.

[0050] Step S134: evaluating the interaction relationship between the pile foundation and the soil according to the pile foundation displacement data and the pile foundation force data, and generating constraint conditions for the pile end constraint, soil constraint and pile body constraint of the pile foundation, thereby obtaining support condition data;

[0051] When analyzing the interaction between the pile foundation and the soil based on the displacement and force data of the pile foundation, the embodiment of the present invention first evaluates the vertical deformation of the bottom end of the pile foundation to generate the constraint condition data of the pile end. By monitoring the deformation behavior of the pile foundation under high load, the support strength of the soil is determined and used as the data source of the soil constraint. At the same time, based on the distribution of stress transfer in the pile body, the horizontal constraint conditions of the pile body are judged to identify the strength of the constraint of the pile foundation by the surrounding soil in the horizontal direction. For example, in soft soil areas, the soil constraint is relatively weak, while in sandy soil areas, the constraint is stronger. The support condition data can provide guidance for the subsequent pile foundation structure design to ensure that the interaction between the pile foundation and the soil is reasonably analyzed.

[0052] Step S135: feature fusion of static load condition classification data, structural deformation characteristic data, stress distribution pattern data and support condition data to obtain static condition characteristic data.

[0053] When the embodiment of the present invention performs feature fusion on the static load condition classification data, structural deformation characteristic data, stress distribution pattern data and support condition data, the different characteristic data are first standardized by the weighted average method, and then the characteristic vectors of each type of data are extracted, and the dimensionality reduction fusion is performed by principal component analysis (PCA), and finally the characteristic data representing the overall static condition is obtained. For example, after integrating multiple features, it can be clearly seen that under static conditions, the pile foundation structure is mainly affected by long-term tidal loads, and its deformation trend is stable and there is no stress concentration phenomenon. The static condition characteristic data provides an important basis for evaluating the structural stability of the pile foundation under normal loads, and supports the decision-making of structural maintenance and safety inspections.

[0054] The present invention classifies and processes environmental load data according to loading mode, amplitude and time sequence, and identifies the working condition through static load working condition standards to obtain static load working condition classification data. This step distinguishes the characteristics of different types of environmental loads, so that the model can identify the load effect under specific static conditions. The generation of static load classification data provides a reference basis for subsequent analysis, which can effectively improve the prediction accuracy of pile foundation response under different environmental conditions. By analyzing the displacement data of pile foundation, deformation characteristics are extracted, including displacement amplitude, deformation trend, deformation rate and mode, which helps to understand the deformation behavior of pile foundation under static load in detail. These characteristic data can accurately reflect the actual deformation of pile foundation under static working conditions and provide a comprehensive characteristic description of structural deformation. Deformation characteristic data can help identify the response law of pile foundation under specific load conditions, facilitate the subsequent analysis of the influence of deformation on the safety and stability of pile foundation, and provide reliable data support for displacement prediction. Through stress distribution pattern recognition based on pile foundation force data, characteristics such as stress concentration area, transfer path and stress level are extracted. The stress distribution pattern can reflect the stress state of the pile foundation structure under static conditions, and provides a reliable basis for determining the key stress areas and possible stress concentration points of the pile foundation. The stress distribution pattern data helps identify the stress characteristics of the pile foundation, optimize the pile foundation structure design and construction process, and effectively reduce the structural risks caused by stress concentration. According to the displacement and stress data of the pile foundation, soil-pile interaction analysis is performed to generate the constraints of the pile end, soil and pile body. This process identifies the mutual influence between the pile foundation and the surrounding soil, and comprehensively evaluates the overall stress conditions and support conditions of the pile foundation to ensure that the model can truly reflect the support characteristics of the structure. The support condition data provides accurate boundary conditions for the displacement prediction model, which helps the model to accurately simulate under specific loads and make the prediction closer to the actual working conditions. The static load condition classification, deformation characteristics, stress distribution pattern and support condition data are feature fused to form comprehensive static condition feature data. Through feature fusion, the model can obtain more comprehensive and consistent working condition information and improve the correlation between data. The static working condition characteristic data lays a solid foundation for the subsequent dynamic prediction model training, enabling the model to achieve higher accuracy under static conditions and optimizing the stability and adaptability of the prediction results. In general, these steps form multi-dimensional characteristic data covering load, deformation, stress and support conditions through meticulous static feature analysis, providing detailed static data support for the model. This data processing process improves the prediction accuracy of the model under static working conditions, and through feature fusion, the model is more adaptable to complex working conditions, which helps to further optimize the reliability of pile foundation lateral displacement prediction.

[0055] Preferably, step S14 comprises the following steps:

[0056] Step S141: extracting dynamic response characteristics of dynamic response parameters of the pile foundation structure based on displacement time history, acceleration response and stress fluctuation based on the real-time monitoring parameter data, thereby obtaining dynamic response characteristic data;

[0057] In order to extract the dynamic response characteristics of the pile foundation structure, the embodiment of the present invention first performs a time-history analysis on the real-time monitored displacement, acceleration and stress data. The use of acceleration time-history data in the time domain can reveal the dynamic response of the pile foundation under specific working conditions, such as the instantaneous acceleration peak value and the vibration recovery time of the pile foundation under the impact of waves. The spectral characteristics of stress fluctuations are analyzed by Fourier transform, and the main frequency components caused by dynamic loads are identified to determine the dynamic response characteristic data. For example, when the pile foundation is located in a coastal area and is impacted by periodic waves, significant response characteristics in the frequency range of 1 Hz to 5 Hz can be detected. This data is used to analyze the structural stability of the pile foundation under different dynamic load conditions.

[0058] Step S142: performing vibration modal analysis according to the dynamic response characteristic data, thereby obtaining vibration modal characteristic data;

[0059] The vibration modal analysis in the embodiment of the present invention utilizes the dynamic response characteristic data, and performs vibration modal analysis on the pile foundation structure through modal analysis software such as Ansys to obtain vibration modal characteristic data. First, the structural model of the pile foundation is imported into the software, the boundary conditions are set, and the load distribution of the typical working condition is applied to the pile foundation, and its natural frequency and vibration mode are extracted through eigenvalue analysis. For example, for a 30-meter-long high pile, it can be observed in the vibration modal analysis that its first-order modal frequency is 1.8Hz and the second-order modal frequency is about 4.3Hz, corresponding to different vibration forms such as lateral swing and vertical deformation. Through these characteristic data, engineers can judge the earthquake resistance and wind resistance of the pile foundation to optimize the structural design and improve stability.

[0060] Step S143: extracting dynamic load characteristics of wave load, wind load and earthquake load from environmental load data, and performing parameter statistics of amplitude, frequency, phase and action direction of dynamic load characteristics, so as to obtain dynamic load characteristic data;

[0061] In order to extract the characteristic data of dynamic loads, the embodiment of the present invention first classifies and analyzes the waves, wind loads and earthquake loads contained in the environmental load data. The impact strength and frequency of the waves are analyzed through the amplitude and frequency distribution of the wave loads; the amplitude and direction of the wind load on the structure are extracted through the statistics of wind speed and wind direction data; and the seismic load extracts the phase difference, amplitude and frequency of the seismic action through the seismic acceleration and stress waveform records. For example, at a coastal high-pile wharf, the average amplitude of the wave load is 5kN, the frequency is about 0.7Hz, and the direction of the wind load is stable at an angle of 30°, with a peak value of 20kN. This characteristic data provides key input parameters for dynamic response analysis and structural design.

[0062] Step S144: evaluating dynamic characteristic parameters according to the dynamic response characteristic data and the vibration modal characteristic data to obtain structural dynamic characteristic data, wherein the dynamic characteristic parameters include stiffness characteristics, mass distribution and energy dissipation of the pile foundation structure;

[0063] The embodiment of the present invention evaluates the dynamic characteristic parameters of the pile foundation structure, including stiffness characteristics, mass distribution and energy dissipation, based on the dynamic response characteristics and vibration modal characteristic data. The structural stiffness can be evaluated by analyzing the vibration frequency and modal vibration shape of the pile foundation. The durability of the pile foundation under dynamic load is determined by detecting the energy dissipation in the vibration experiment. Assuming that the first modal vibration frequency of the pile foundation under seismic load is 2 Hz, its energy dissipation rate is detected to be 5% through amplitude attenuation, indicating that the pile foundation has a high seismic resistance during vibration, thereby obtaining structural dynamic characteristic data. These data can further optimize the pile foundation structure and improve its durability and seismic resistance.

[0064] Step S145: performing characteristic correlation analysis on the dynamic response characteristic data, the vibration mode characteristic data, the dynamic load characteristic data and the structural dynamic characteristic data, so as to obtain dynamic working condition characteristic data.

[0065] In order to generate dynamic working condition characteristic data, the embodiment of the present invention performs correlation analysis on dynamic response, vibration mode, dynamic load and structural dynamic characteristic data. The response characteristics of the pile foundation under different load conditions can be revealed through correlation analysis. Using a multivariate regression model, the modal characteristics, response amplitude, and frequency under different working conditions are correlated with the corresponding dynamic load characteristic data to identify the pile foundation response under a specific load combination. For example, when wind load and seismic load act in combination, by comparing the displacement response of the pile foundation under each mode, it can be found that the amplitude increase during the combined action reaches 30%, which is helpful for extracting dynamic working condition characteristics and providing decision support for real-time monitoring and dynamic control of pile foundation structures.

[0066] The present invention obtains the dynamic response characteristics of the pile foundation structure by extracting the displacement time history, acceleration response and stress fluctuation in the real-time monitoring data. This step provides the real response of the pile foundation structure under dynamic conditions and reveals the dynamic behavior of the pile foundation under different dynamic loads. The dynamic response characteristic data provides detailed basic data for subsequent vibration modal analysis and dynamic characteristic evaluation, ensures the model's ability to capture dynamic responses, and helps to improve the dynamic prediction accuracy of the model. Through the vibration modal analysis of the dynamic response characteristic data, the vibration modal characteristic data is obtained to help identify the characteristics of the pile foundation structure such as the natural frequency, vibration mode and damping ratio. These characteristics are important indicators of dynamic response and reflect the interactive relationship between the vibration characteristics of the structure and the external load. The vibration modal characteristic data enables the model to better understand the dynamic response of the pile foundation structure at different frequencies, ensure the prediction accuracy of the model under various dynamic conditions, and especially provide more reliable predictions under the conditions of complex fluctuating loads. By extracting the characteristics of dynamic loads such as waves, wind loads and earthquakes from the environmental load data, the detailed parameters of these loads in amplitude, frequency, phase and direction of action are obtained. This process provides the model with an accurate description of various complex loads and enhances the adaptability of the model under multi-source loads. The generation of dynamic load characteristic data can ensure that the model can better simulate the effects of various dynamic loads under real working conditions and effectively improve the response accuracy of the model under fluctuating and sudden loads. Combined with dynamic response characteristic data and vibration mode characteristic data, the dynamic characteristic parameters such as stiffness characteristics, mass distribution and energy dissipation of the pile foundation structure are evaluated. The dynamic characteristic data describes the stability and resistance capacity of the pile foundation structure under dynamic action, and provides the necessary stiffness and energy dissipation indicators for the prediction model. The structural dynamic characteristic data not only supports dynamic displacement prediction, but also can evaluate the durability and safety of the structure under different load conditions, which helps to more accurately predict the long-term performance of the structure under dynamic load conditions. The dynamic response characteristic data, vibration mode characteristic data, dynamic load characteristic data and structural dynamic characteristic data are correlated and analyzed to form dynamic working condition characteristic data. Through feature correlation, the model can integrate multiple dynamic features to more accurately capture the overall response of the pile foundation under dynamic conditions. The formation of dynamic working condition characteristic data ensures the comprehensive response capability of the model to various dynamic working conditions, enabling it to provide more accurate and reliable displacement prediction results under complex working conditions. In general, these steps effectively improve the adaptability and prediction accuracy of the model to complex dynamic environments by comprehensively extracting and analyzing the dynamic working condition characteristics of the pile foundation structure. This series of feature extraction and analysis lays a solid foundation for the dynamic response part of the pile foundation lateral displacement prediction model, ensuring that the displacement prediction results under different working conditions are accurate and highly reliable.

[0067] Preferably, step S142 includes the following steps:

[0068] Step S1421: extracting the natural frequency of the pile foundation structure from the dynamic response characteristic data to obtain natural frequency characteristic data;

[0069] In order to extract the natural frequency of the pile foundation structure, the embodiment of the present invention first performs spectrum analysis on the dynamic response characteristic data, and uses the fast Fourier transform (FFT) technology to convert the time domain data into frequency domain data, so as to obtain the response amplitude of the pile foundation at different frequencies. The natural frequency is identified by looking for the significant frequency peak position in the spectrum diagram. For example, in the pile foundation structure of the coastal high-pile wharf, it is found through FFT analysis that the frequency has obvious peaks at 1.5Hz and 3.8Hz, representing the first and second order natural frequencies of the pile foundation. These data provide important natural frequency characteristic data for subsequent modal analysis.

[0070] Step S1422: performing modal vibration shape analysis based on the natural frequency characteristic data, extracting the vibration modal shape of the pile foundation structure, and calculating the amplitude and phase characteristics of each order mode, thereby obtaining modal vibration shape data;

[0071] The embodiment of the present invention performs modal vibration type analysis on the pile foundation structure based on the extracted natural frequency characteristic data. First, the structural model is input into the modal analysis software, such as Ansys or Matlab, and a small simulated load is applied at the natural frequency, and the modal vibration type is extracted by calculating the displacement response of the structure. The amplitude and phase characteristics of each mode are calculated in the analysis. For example, in the first-order mode of 2Hz, the amplitude of the top of the pile foundation is 0.005m, and there is a phase difference of 180° relative to the base. These modal vibration type data can intuitively show the vibration behavior of the pile foundation in different modes, providing data support for structural health assessment and improved design.

[0072] Step S1423: Calculating the damping ratio of each mode of the pile foundation structure based on the half-power method for the dynamic response characteristic data and the modal vibration shape data, thereby obtaining damping characteristic data;

[0073] In order to calculate the damping ratio of each mode of the pile foundation structure, the embodiment of the present invention adopts the half-power method to calculate the damping by analyzing the bandwidth characteristics of the dynamic response characteristic data and the modal vibration data. First, the natural frequency of a specific mode is selected, and then the peak frequency and the half-power point frequency of the response curve are recorded near the frequency. The damping ratio is calculated using the formula. For example, for the first-order mode, the peak value of the response amplitude at 1.5Hz is 0.003m, and the half-power point frequencies are 1.4Hz and 1.6Hz respectively. The damping ratio is calculated to be 3%. The damping characteristic data can reflect the vibration energy dissipation capacity of the structure and provide an important reference for the optimization of seismic design.

[0074] Step S1424: Analyze the changing rules of the natural frequency characteristic data, the modal vibration shape data and the damping characteristic data based on the time series, and evaluate the time-varying characteristics of the dynamic characteristics of the pile foundation structure, so as to obtain the vibration modal characteristic data.

[0075] The embodiment of the present invention performs time-varying characteristic analysis based on natural frequency, modal vibration shape and damping characteristic data, and evaluates the changing trend of the dynamic characteristics of the pile foundation structure over time through the time series analysis method. The vibration modal parameters are modeled using an autoregressive model (AR) to observe the changes in natural frequency and damping ratio at different time points. For example, long-term monitoring results show that after 6 months, the first-order natural frequency dropped from 1.5Hz to 1.48Hz, and the damping ratio increased from 3% to 3.2%, reflecting possible minor damage or performance degradation to the structure. Through this time-varying characteristic evaluation, potential damage to the structure can be warned in advance, providing data support for maintenance decisions.

[0076] The present invention obtains natural frequency characteristic data, which is a basic parameter of structural vibration, by extracting the natural frequency in the dynamic response characteristic data. The natural frequency reflects the free vibration characteristics of the structure without external excitation, and can reveal the overall stiffness and mass distribution of the structure. Extracting the natural frequency data enables the model to accurately identify the natural vibration characteristics of the pile foundation structure, helps to predict the response of the pile foundation under a specific frequency excitation, and provides a basis for subsequent modal analysis. Based on the natural frequency characteristic data, the vibration modal morphology of the pile foundation structure is analyzed, including the vibration amplitude and phase characteristics, to obtain the modal vibration data of each order. The modal vibration data reveals the deformation mode and relative displacement distribution of the structure under different modes, which is particularly critical for identifying the deformation characteristics of the structure under different working conditions. Modal vibration analysis not only improves the model's understanding of the dynamic behavior of the pile foundation structure, but also provides vibration amplitude and phase data, which can be used to predict the deformation trend and dynamic stability of the pile foundation under external loads. The damping ratio of the dynamic response characteristic data and the modal vibration data is calculated using the half-power method to obtain the damping characteristic data. The damping ratio reflects the ability of the pile foundation structure to dissipate energy during vibration and has an important influence on the stability of the dynamic response. The damping characteristic data provides the model with key energy loss information, enabling it to more accurately evaluate the vibration attenuation of the pile foundation structure under dynamic loads, helping to improve the prediction ability of the structure's seismic and wind load resistance. By analyzing the time series of natural frequency characteristic data, modal vibration data, and damping characteristic data, the law of the dynamic characteristics of the pile foundation structure changing over time is evaluated to obtain vibration modal characteristic data. Time-varying characteristic evaluation can capture the gradual change of structural characteristics over time, especially the performance degradation caused by load, environmental influence or material aging. This step provides the attenuation characteristics and time-varying response of the pile foundation structure under long-term dynamic loads, providing a basis for the long-term prediction and reliability evaluation of the model, helping the model to dynamically adjust the prediction parameters and improve the adaptability of the prediction. Overall, these steps provide an in-depth analysis of the dynamic characteristics of the pile foundation structure, enabling the model to more comprehensively understand and predict the response changes of the structure under long-term and multiple dynamic conditions. By extracting natural frequencies, modal vibration shapes and damping characteristics and performing time-varying analysis on them, the prediction accuracy and reliability of the model are greatly improved, which can effectively support the durability and safety management of pile foundation structures.

[0077] Preferably, step S2 comprises the following steps:

[0078] Step S21: extracting multi-source load characteristics from the pile foundation structure working condition data, thereby obtaining multi-source load characteristic data;

[0079] In the multi-source load feature extraction of the pile foundation structure, the embodiment of the present invention first performs a sub-item feature analysis on the monitored environmental loads, including wave loads, wind loads, and earthquake loads, and extracts the amplitude, frequency, and direction of action of each load through Fourier analysis. For example, the earthquake wave and wave impact data obtained by the acceleration sensor and pressure sensor, the average amplitude of the wave load obtained by feature extraction is 5kN / m 2 , the frequency is 0.6Hz, and the action direction is perpendicular to the shoreline. The multi-source load characteristic data provides an accurate data input basis for the subsequent coupling effect analysis.

[0080] Step S22: performing load coupling effect analysis based on multi-source load characteristic data, and performing coupling calculation through the mutual influence and superposition effect between environmental loads to generate coupling load data;

[0081] In the load coupling effect analysis of the embodiment of the present invention, the finite element software is used to perform coupling calculation by superimposing the effects of wave load and wind load. The coupling load data is generated by the mutual influence between environmental loads, such as the amplification effect of wave impact on wind pressure. Specifically, in the analysis, it is assumed that the wave load and wind load are orthogonally superimposed. The calculation results show that the superposition effect makes the coupling load peak reach 7.5kN / m 2 , the influence of wind pressure on pile foundation structure under wind speed change is considered. The coupled load data reflects the load distribution under complex environmental conditions.

[0082] Step S23: Analyze the temporal and spatial distribution characteristics, effects and change rules of the load action on the multi-source load characteristic data and the coupled load data, so as to obtain the load action data;

[0083] The embodiment of the present invention performs temporal and spatial distribution characteristic analysis on multi-source load characteristic data and coupled load data to identify the concentrated area and variation law of load action. Statistical methods are used to analyze time series data and combined with spatial grid division. For example, in the area from 0 to 2m at the bottom of the pile foundation, the load action frequency is high and the amplitude is significant. The time-averaged load value of this area is 6kN / m 2 , peak value 8kN / m 2 The load action data can reflect the stress mode of the pile foundation under the change of environmental load and provide support for the structural safety assessment.

[0084] Step S24: simulating the response of the pile foundation under different load combination conditions according to the coupled load data, extracting the soil-pile interaction characteristics, and generating soil-pile force data, wherein the response simulation under different load combination conditions includes soil resistance, pile deformation, and soil-pile interface contact characteristics;

[0085] The embodiment of the present invention simulates the response of the pile foundation under different load combination conditions based on the coupling load data, and uses the finite element method to analyze the soil-pile interaction characteristics under different conditions. Through simulation, it is found that when the wind speed increases to 12m / s, the lateral displacement of the pile foundation increases, the soil resistance increases to 10kN / m, and the maximum deformation of the pile body is 3mm. The soil-pile interface contact characteristics show that the soil has a strong constraint at a depth of 2m. The analysis results reveal the nonlinear response of the soil-pile system under load combination conditions, and the generated soil-pile force data provides the necessary parameter support for structural stability analysis.

[0086] Step S25: generating stress distribution, deformation coordination and constraint conditions between the soil and the pile foundation based on the soil-pile force data and the load action data, thereby obtaining soil-pile interaction characteristic data;

[0087] The embodiment of the present invention evaluates the stress distribution and constraint conditions of the pile foundation and the surrounding soil based on the soil-pile force data and combined with the load data. Through stress field analysis, it is found that the stress concentration area generated by the pile foundation under the wave load is located at the bottom of the pile foundation, and the pressure value reaches 15MPa. The soil constraint is mainly around the pile body at a depth of 1m to 3m. The soil-pile interaction characteristic data provides a basis for the design and durability analysis of the pile foundation structure by accurately simulating the constraint force of the soil on the pile foundation under load.

[0088] Step S26: Perform soil-pile energy dissipation and stress path evolution analysis based on the soil-pile force data and the soil-pile interaction characteristic data, so as to obtain soil-pile response data.

[0089] The embodiment of the present invention uses soil-pile force data and soil-pile interaction characteristic data to perform energy dissipation and stress path analysis. By calculating the stress path under different load conditions, it is found that when strong wave loads act, the dissipated energy of the soil-pile system increases significantly, reaching 50J / m 2 , and the stress path shows nonlinear variation characteristics. This analysis reveals the energy dissipation mechanism of the pile foundation structure under continuous load and the variation trend of the internal stress path. The generated soil-pile response data can be used to predict the performance degradation of the pile foundation under long-term stress.

[0090] The present invention obtains multi-source load characteristic data by extracting the characteristics of different load sources (such as wind, waves, earthquakes, etc.) in the working condition data of the pile foundation structure. This step helps to decompose the individual action characteristics of various loads and provides data support for the subsequent coupling effect analysis. Extracting multi-source load characteristic data enables the model to distinguish the independent influences of different loads, thereby providing detailed information for load characteristic analysis and laying a foundation for accurately predicting the behavior of pile foundations under composite loads. Load coupling effect analysis is performed on the basis of multi-source load characteristic data, and coupled load data is generated in combination with the mutual influence between environmental loads. The coupling effect analysis reveals the superposition and mutual influence between multi-source loads, especially the comprehensive effects under the conditions of wave and wind loads, earthquake and soil reaction, etc. This analysis provides accurate load input for pile foundation response under load combinations and complex working conditions, making the model more realistic and reliable when simulating actual environmental conditions, and improving the accuracy of load prediction. Through the analysis of multi-source load characteristic data and coupled load data, the spatiotemporal distribution characteristics of load action, as well as the effect and change law of action are obtained. This step provides an important reference for understanding the distribution characteristics of loads in spatial range and time dimension, especially the application characteristics of multi-source loads at different locations and times. This analysis provides detailed dynamic input for the overall response of pile foundation under load, helping to improve the spatial accuracy and temporal consistency of prediction, especially in complex environments, it can better capture the dynamic changes of loads. Based on the coupled load data, the response of pile foundation under different load combinations is simulated, and the soil-pile interaction characteristics such as soil resistance, pile deformation and soil-pile interface contact characteristics are extracted to generate soil-pile force data. This simulation covers the pile foundation response under different working conditions and deeply depicts the complex characteristics of soil-pile interaction. This step provides the model with real soil-pile interface characteristic input, enhances the model's ability to predict the dynamic response of pile foundation structure under different load conditions, and especially helps to identify and estimate the potential failure mode of soil-pile system. Based on soil-pile force data and load data, the stress distribution, deformation coordination and constraint conditions between soil and pile foundation are analyzed to generate soil-pile interaction characteristic data. The analysis of stress distribution and constraint conditions provides the internal force distribution of the pile foundation under external loads, and further reveals the stress transfer and mutual coordination characteristics between soil and piles. By generating soil-pile interaction characteristic data, the model can accurately reflect the stress state and constraint conditions of the pile foundation under different load conditions, and improve the stability prediction and load resistance evaluation of the pile foundation structure under complex load conditions. Based on the soil-pile force data and soil-pile interaction characteristic data, the energy dissipation and stress path evolution analysis of the soil-pile system are carried out to obtain the soil-pile response data. This step evaluates the dynamic changes of energy dissipation and stress transfer path of the soil-pile interface under load, and provides the response behavior of the pile foundation under complex stress conditions.Energy dissipation and stress path analysis reveal the attenuation characteristics and stress evolution law of the soil-pile system under long-term and variable loads, providing a scientific basis for the durability and fatigue resistance of the pile foundation. The model can optimize the safety prediction of the pile foundation structure in long-term operation and effectively evaluate the potential failure risk. In summary, these steps make the model highly accurate and reliable in predicting pile foundation structures under multi-source load conditions through detailed load characteristic analysis, coupling effect calculation, soil-pile interaction characteristic generation and energy dissipation analysis. These analyses significantly improve the load adaptability and dynamic stability prediction of the pile foundation structure, and provide scientific support for the long-term reliability and durability management of pile foundations in complex environments.

[0091] Preferably, step S3 comprises the following steps:

[0092] Step S31: performing material mechanical property analysis on the soil-pile response data to obtain material performance characteristic data, wherein the material mechanical property analysis includes material strength degradation assessment, elastic modulus variation analysis, plastic deformation feature extraction, and fatigue damage degree calculation;

[0093] In the material mechanical properties analysis of soil-pile response data, the embodiment of the present invention evaluates the strength degradation of the pile foundation material by fitting the stress-strain curves of the pile foundation under different loads, and analyzes the changing trend of the elastic modulus. In the specific operation, the residual strain data after each loading is extracted to evaluate the plastic deformation, and the degree of fatigue damage is calculated in combination with the measured data. For example, the elastic modulus of the concrete material located in the top area of ​​the pile foundation decreases by about 10% within 10 years, and the fatigue damage accumulation rate reaches 15%. The strength degradation rate of the material increases significantly under the impact load, and the generated material performance characteristic data provides an effective reference for the durability analysis of the pile foundation.

[0094] Step S32: evaluating material performance degradation based on the material performance characteristic data and the pre-acquired long-term monitoring data of the environment in which the pile foundation is located, thereby obtaining material status data;

[0095] The embodiment of the present invention combines the material performance characteristic data and the long-term monitoring data of the environment in which the pile foundation is located to evaluate the degradation of the pile foundation material performance. Through the historical data of temperature and humidity and the degree of salt spray erosion, the material degradation state is quantitatively analyzed, and the degradation rate is calculated. In practical applications, assuming that the pile foundation in a coastal area is exposed to high humidity and high salt environment for a long time, the degradation assessment shows that the strength of the surface concrete of the pile foundation is reduced by about 15%, and the internal microcracks increase. The generated material status data is used to formulate subsequent maintenance and repair plans.

[0096] Step S33: using environmental monitoring equipment to collect environmental parameters such as temperature, humidity and pH value, thereby obtaining environmental parameter data;

[0097] The embodiment of the present invention collects environmental parameters such as temperature, humidity and pH value in the area around the pile foundation in real time through environmental monitoring equipment to generate environmental parameter data. The specific method is to use distributed temperature and humidity sensors and pH sensors to collect data every hour. For example, the average temperature around the pile foundation is detected to be 20°C, the humidity is 85%, and the pH value is 6.5. These environmental parameter data reflect the changes in the environmental conditions around the pile foundation and provide basic data for the subsequent accelerated degradation factor evaluation.

[0098] Step S34: evaluating the accelerated degradation factor according to the environmental parameter data and the material status data, thereby obtaining environmental impact characteristic data;

[0099] The embodiment of the present invention uses environmental parameter data and material status data to evaluate the accelerated degradation factor and calculate the impact of the environment on the accelerated degradation of pile foundation materials. By establishing an accelerated degradation factor model, the impact of parameters such as humidity, temperature, and pH on the material degradation rate is quantified. In a corrosive environment, for every 10% increase in humidity, the material degradation rate increases by about 5%; when the temperature rises to 30°C, the degradation rate increases to 1.5 times the original rate. The generated environmental impact characteristic data provides important support for the material durability analysis of pile foundations under different environmental conditions.

[0100] Step S35: extracting time domain features and frequency domain features from the real-time monitoring parameter data, thereby obtaining multi-dimensional monitoring feature data;

[0101] The embodiment of the present invention extracts time domain and frequency domain features from real-time monitoring parameter data to obtain the force and displacement characteristics of the pile foundation in different time periods. Fast Fourier transform is used to perform spectrum analysis on the data to identify the main frequency distribution and time domain characteristics of displacement and load. For example, the main vibration frequency of the pile foundation structure is extracted to be 1.2Hz, and the peak displacement reaches 3mm during the typhoon. The multi-dimensional monitoring feature data can reflect the dynamic response characteristics of the pile foundation in a complex environment, providing rich input data for the subsequent construction of the correlation model.

[0102] Step S36: establishing a displacement-environment-load association model based on the multi-dimensional monitoring characteristic data and the environmental impact characteristic data, and performing feature extraction on the association model to obtain association characteristic data.

[0103] The embodiment of the present invention establishes a displacement-environment-load correlation model based on multi-dimensional monitoring feature data and environmental impact feature data, and analyzes the displacement response relationship of the pile foundation structure under different environmental and load conditions. Through machine learning algorithms such as random forests, key features in the correlation model are extracted, such as the significant change pattern of displacement under wind load and high humidity conditions. Calculations show that when the humidity increases to more than 90% during a typhoon, the peak displacement increases to 1.8 times the normal level. The generated correlation feature data provides a key analysis basis for the long-term stability evaluation of the pile foundation structure.

[0104] The present invention analyzes the soil-pile response data for material strength degradation, elastic modulus change, plastic deformation characteristics and fatigue damage degree to obtain material performance characteristic data. This analysis can reveal the changes in the internal mechanical properties of the pile foundation under load and environmental stress, especially the strength and elasticity reduction of the pile foundation material. These mechanical characteristic analyses provide key parameters for the dynamic stability and durability evaluation of the material, so that the model can accurately reflect the bearing capacity of the material in long-term predictions, and improve the fatigue life evaluation capability of the pile foundation. By combining the material performance characteristic data with the long-term monitoring data of the environment in which the pile foundation is located, the degradation state of the pile foundation material can be evaluated and material state data can be generated. This step reflects the performance changes of the pile foundation material under the influence of long-term environment, especially the degradation rate and influencing factors. Material degradation evaluation provides a scientific basis for the durability management and safety prediction of the pile foundation structure, so that the model can more accurately evaluate the service life of the pile foundation under complex working conditions according to different environmental factors, and effectively prevent structural failure caused by material degradation. Environmental monitoring equipment is used to collect environmental parameter data such as temperature, humidity, pH value, etc., reflecting the actual environmental conditions around the pile foundation. Factors such as temperature, humidity, and pH directly affect the degradation rate of pile foundation materials, especially in harsh environments such as high humidity and high pH. Collecting environmental parameter data provides real and detailed data support for subsequent degradation assessment and environmental impact analysis, which helps to identify key environmental factors that have a significant impact on material degradation, making degradation assessment more accurate. Based on environmental parameter data and material status data, through the analysis of accelerated degradation factors, the accelerated degradation effect of environmental factors such as temperature, humidity, and pH on pile foundation materials can be identified, and environmental impact characteristic data can be generated. Accelerated degradation factor assessment provides specific impact weights of different environmental conditions on material performance. Accelerated degradation factor analysis helps predict the long-term degradation of pile foundations in harsh environments, especially durability management under extreme climatic conditions, provides a scientific basis for pile foundation maintenance cycles and material selection, and improves the environmental adaptability of the structure. Time domain and frequency domain feature extraction is performed on real-time monitoring parameter data to obtain multi-dimensional monitoring feature data, including the time series and frequency characteristics of displacement, stress, and load changes. These multi-dimensional characteristic data provide comprehensive monitoring information for the dynamic response of pile foundations, and can effectively reflect the behavior patterns of pile foundations under various loads. The combined analysis of time domain and frequency domain characteristics improves the model's ability to identify response characteristics, allowing the prediction model to dynamically track changes in structural states, ensuring real-time monitoring and accurate prediction of pile foundation behavior. A displacement-environment-load correlation model is established based on multi-dimensional monitoring characteristic data and environmental impact characteristic data, and correlation characteristic data is generated by extracting features from the model. This model reflects the relationship between pile foundation displacement, environmental factors, and load effects, and is the core support for model prediction.The construction and feature extraction of the correlation model realize the prediction of the overall behavior of the pile foundation under complex environmental conditions, so that the model can dynamically adjust the prediction parameters, improving the response accuracy and prediction applicability under various working conditions. In summary, these steps enhance the adaptability and accuracy of the model to long-term degradation and changing environments through detailed analysis of material properties and environmental factors, extraction of environmental influencing factors, and construction of displacement-environment-load correlation models. This process ensures the safety of pile foundations in long-term use and provides accurate and reliable data support and scientific basis for pile foundation maintenance management and performance prediction in complex environments.

[0105] Preferably, step S34 includes the following steps:

[0106] The accelerated degradation factor is evaluated based on the environmental parameter data and material status data to obtain the environmental impact characteristic data. The accelerated degradation factor is evaluated specifically by the temperature stress coefficient through the Arrhenius formula, the humidity expansion coefficient is evaluated through the Arrhenius humidity-temperature acceleration model, and the corrosion rate coefficient is calculated based on Faraday's law.

[0107] When evaluating the accelerated degradation factor, the embodiment of the present invention first uses the temperature and humidity values ​​in the environmental parameter data to calculate the temperature stress coefficient and the humidity expansion coefficient. In the specific operation, the monitoring data of a pile foundation is selected, and the average temperature is recorded as 25°C and the humidity is 80%. According to the Arrhenius formula, the temperature stress coefficient K is calculated. T The formula is Where A is the pre-factor, E a is the activation energy, R is the gas constant, and T is the absolute temperature. Assume that the activation energy E a is 50 kJ / mol, and K T ≈1.5. Then, the Arrhenius humidity-temperature acceleration model was applied to calculate the humidity expansion coefficient K H For example, if the ambient humidity varies between 70% and 90%, the expansion coefficient is set to 0.02% / °C, and the expansion acceleration factor is assumed to be 1.3 at the current humidity level, and K is obtained. H ≈0.026. Through the above calculations, the combined data of temperature stress coefficient and humidity expansion coefficient are obtained to form preliminary environmental impact characteristic data, laying the foundation for further corrosion rate evaluation. When evaluating the corrosion rate coefficient, Faraday's law is used for calculation. The specific formula is: Where I is the current, n is the transfer number, F is the Faraday constant, and dM / dt is the corrosion rate. Assume that the current density in a certain corrosion environment is 10mA / cm 2 , the estimated transfer number n is 2, and the corrosion rate coefficient is calculated as Where F is about 96485C / mol, we get KC ≈0.00012g / cm 2 h. Through this method, combined with the previous environmental stress and humidity expansion data, comprehensive analysis, the environmental impact characteristic data finally generated provides a more comprehensive assessment of the deterioration of pile foundation materials and provides a scientific basis for the formulation of subsequent structural monitoring and maintenance strategies.

[0108] In the long-term use of the pile foundation of the present invention, environmental factors such as temperature, humidity and corrosion will significantly affect the degradation rate of the material. Therefore, the evaluation of accelerated degradation factors such as temperature, humidity and corrosion can provide a key basis for the long-term reliability prediction of the pile foundation material. The accelerated degradation factor is scientifically evaluated using environmental parameter data and material state data, and the generated environmental impact characteristic data is of great significance to the stability prediction and maintenance strategy optimization of the pile foundation structure. The temperature stress coefficient is calculated by the Arrhenius formula, and the influence of temperature on the material degradation rate can be accurately evaluated. The Arrhenius formula provides a reliable scientific model for predicting the degradation process of materials under different temperature conditions by describing the rate at which chemical reactions change with temperature. The evaluation of the temperature stress coefficient can help predict the service life of the pile foundation under extreme temperatures or long-term temperature fluctuations, especially can identify the trend of accelerated degradation under high temperature conditions, facilitate the formulation of protection and maintenance strategies under high temperature environments, and extend the durability of pile foundation materials. The humidity expansion coefficient is evaluated by the Arrhenius humidity-temperature acceleration model, which can reflect the influence of humidity on the expansion and degradation of pile foundation materials at different temperatures. The humidity-temperature acceleration model comprehensively considers the coupling effect of humidity and temperature, making the assessment of humidity effects more accurate, especially for humidity-sensitive materials. The evaluation of humidity expansion coefficient can reveal the expansion and deterioration rate of pile foundation materials in high humidity environments, which is convenient for pretreatment of pile foundation materials or selection of more suitable materials in high humidity environments to prevent material performance degradation caused by humidity, such as reduced strength or reduced durability. The corrosion rate coefficient is calculated by Faraday's law, and the effect of corrosion on material degradation is quantified based on the relationship between the electrochemical reaction rate and current density of the material. Faraday's law can accurately describe the weight loss rate of materials under different corrosion conditions, providing a scientific basis for the prediction of degradation under long-term immersion and salt spray environments. The evaluation of the corrosion rate coefficient is particularly suitable for pile foundation application scenarios in coastal or high-salinity areas. It can predict the failure trend of pile foundation materials in corrosive environments, help select materials with higher corrosion resistance, or formulate anti-corrosion construction and maintenance measures in advance. Through the evaluation of temperature stress coefficient, humidity expansion coefficient and corrosion rate coefficient, the generated environmental impact characteristic data provides a multi-factor coupling characteristic system for the material degradation prediction of pile foundation structures. This comprehensive environmental impact analysis model can accurately reflect the degradation pattern of materials in complex environments. The acquisition of environmental impact characteristic data enhances the life prediction model of pile foundation materials, enabling the model to effectively distinguish the degradation effects of different environmental conditions and improve the accuracy of structural health monitoring. At the same time, comprehensive consideration of multiple accelerated degradation factors makes the model applicable to more diverse environments, ensuring the wide applicability and scientific nature of the prediction. In summary, this step provides a quantitative evaluation standard for the long-term degradation prediction of pile foundation materials based on the evaluation of accelerated degradation factors of different environmental parameters.By evaluating the coefficients of key environmental factors such as temperature, humidity and corrosion, the model can more accurately reflect the reliability of pile foundations under extreme conditions, guide maintenance and material selection, extend the service life of the structure, and improve safety and economy.

[0109] Preferably, step S4 comprises the following steps:

[0110] Step S41: constructing a deep neural network structure based on the associated feature data, and using a back propagation algorithm to perform model training, thereby obtaining prediction model parameters;

[0111] The embodiment of the present invention constructs a deep neural network structure based on associated feature data. A network model suitable for time series prediction, such as a long short-term memory (LSTM) network, is selected as the basic architecture. Assume that the input layer contains 50 neurons, then two LSTM layers are set, each containing 100 units, and finally a fully connected layer is connected to output the displacement prediction value of the pile foundation. Then, the model is trained using the back propagation algorithm based on the collected historical data. In the specific training process, the learning rate is set to 0.001, the mean square error (MSE) is used as the loss function, the model parameters are adjusted through each epoch, and 1000 epochs are continued until the loss value converges to a preset threshold (for example, 0.01). After the training is completed, the model parameters are saved for subsequent predictions.

[0112] Step S42: performing time series decomposition on the load action data, and extracting the periodicity characteristics, trend characteristics and random characteristics of the load, so as to obtain a load time series characteristic model;

[0113] The embodiment of the present invention performs time series decomposition on load action data, firstly adopts seasonal decomposition method (such as STL decomposition) to decompose the load data into trend, seasonal and random components. Assuming that the load data monitored over a period of time (such as 12 months) is [200, 220, 250, 230, 210, 240, 300, 280, 270, 290, 310, 320] kN, first calculate its moving average to obtain the trend component. Then, calculate the periodic component (such as monthly fluctuations), extract the random component, and analyze it through Python's statsmodels library, and finally form a load time series characteristic model to describe the main trend, periodic fluctuation and random characteristics of load changes.

[0114] Step S43: performing coupling analysis on the load time series characteristic model and the prediction model parameters to construct a time series correlation prediction model, thereby obtaining time series prediction parameter data;

[0115] When the embodiment of the present invention couples the load time series characteristic model with the prediction model parameters, the result of the load time series characteristic extraction is first combined with the trained deep neural network parameters. The extracted trend and seasonal components are used as inputs, and the constructed prediction model is used for the next step of coupling analysis. Assuming that the extracted trend characteristics are [215, 230, 260] kN and the seasonal characteristics are [20, -10, 30] kN, the model is built in combination with the historical load data, and the load time series characteristic model is coupled with the deep learning model by weighted sum to form a time series correlation prediction model, and obtain the time series prediction parameter data, which provides the expected load changes of the pile foundation in the future.

[0116] Step S44: optimizing the prediction accuracy based on the attention mechanism according to the time series prediction parameter data, thereby generating dynamic prediction control data;

[0117] The embodiment of the present invention optimizes the prediction accuracy based on the attention mechanism according to the time series prediction parameter data. In the specific implementation, the attention layer is first introduced into the deep neural network to better capture the input features that have the greatest impact on future predictions. Assume that through training, it is found that the load changes in specific time periods (such as daily peak hours) have a greater impact on the overall prediction results. Therefore, higher weights are assigned to these features in the model, and the model is optimized by adjusting the attention mechanism parameters so that it pays more attention to the load feature data at critical moments, thereby generating dynamic prediction control data and improving the accuracy of the prediction results.

[0118] Step S45: performing prediction error analysis on the dynamic prediction control data, calculating the deviation between the predicted value and the measured value, thereby generating prediction error characteristic data;

[0119] When the embodiment of the present invention performs prediction error analysis on dynamic predictive control data, the actual monitoring value is first collected for comparison with the predicted value. Assuming that the predicted value at a certain point in time is 310 kN, and the actual monitoring value is 300 kN, the prediction error is calculated to be 310-300=10 kN. Such calculations are performed on all predicted values ​​and measured values ​​to obtain a set of error data. The root mean square error (RMSE) and absolute percentage error (MAPE) are calculated through statistical analysis to evaluate the overall prediction performance of the model and generate prediction error characteristic data.

[0120] Step S46: performing sensitivity analysis on the prediction model parameters according to the prediction error characteristic data, thereby obtaining parameter sensitivity data;

[0121] The embodiment of the present invention performs sensitivity analysis of the prediction model parameters based on the prediction error characteristic data. First, a set of reference parameter values ​​(such as learning rate, number of hidden layer units, etc.) is set to monitor the change of prediction error when the parameters change. Using sensitivity analysis methods (such as local sensitivity analysis), the learning rate is changed (such as from 0.001 to 0.0005) and the prediction is re-performed to observe the degree of change in the prediction error. By recording the degree of influence of different parameter changes on the prediction results, parameter sensitivity data is obtained, and the parameters that have the greatest influence on the prediction effect are identified, providing a basis for subsequent optimization.

[0122] Step S47: Adaptively update the prediction model parameters according to the dynamic prediction control data and the parameter sensitivity data, so as to obtain optimized model parameters.

[0123] The embodiment of the present invention adaptively updates the prediction model parameters according to the dynamic prediction control data and parameter sensitivity data. First, the key parameters (such as learning rate and number of hidden units) identified in the sensitivity analysis are selected, and the model is retrained using an adaptive algorithm (such as the Adam optimizer). Assuming that it is found in the sensitivity analysis that reducing the learning rate can significantly improve the prediction performance, the learning rate is adjusted to 0.0005, and the model is continued to be trained until the error reaches a new lower level. After the adaptive update, the optimized model parameters are obtained, which further improves the accuracy and reliability of the model in future load forecasting.

[0124] The present invention utilizes a deep neural network (DNN) to process multi-source associated feature data of a pile foundation structure, and the DNN can capture complex displacement feature patterns in a nonlinear and high-dimensional feature space. The back propagation algorithm continuously optimizes the model parameters through error feedback, so that the model can better adapt to the actual data characteristics. The prediction model parameters obtained by deep neural network training have a high generalization ability, and can cope with a variety of working conditions and complex load characteristics, thereby improving the prediction accuracy of the model. The load action data is decomposed into time series, and the periodicity, trend and randomness characteristics are extracted, which can accurately describe the dynamic change characteristics of the load. This time series decomposition enables the model to identify the different effects of the load on the pile foundation structure, and further constructs a load time series feature model. The feature model obtained by time series decomposition can help identify the load change pattern, so that the model has a stronger foresight when predicting future load effects, improves the load prediction accuracy, and provides more stable input data for the displacement prediction of the pile foundation structure. The load time series feature model is coupled with the prediction model parameters to construct a time series correlation prediction model. This coupling analysis can better associate the response relationship between load and displacement, so that the prediction model can dynamically reflect the real-time impact of the load on the pile foundation structure. The construction of a time-series correlation prediction model can improve the dynamic adaptability of the prediction model, so that the model also has good coping ability when dealing with sudden load changes, and enhances the model's ability to predict the displacement of pile foundations in a timely manner. By introducing the attention mechanism, the model can focus on the key load features that have a greater impact on the prediction, reduce the interference of irrelevant or minor features, and thus improve the accuracy of the prediction results. The introduction of the attention mechanism effectively improves the model's ability to analyze complex load data, making the prediction results more robust and accurate, and providing high-quality data support for the displacement prediction of pile foundation structures. By calculating the deviation between the predicted value and the measured value, the prediction error characteristic data is obtained, and the error distribution of the model under different working conditions is identified. This error analysis can timely discover the source of the model's deviation and provide a basis for subsequent optimization. The error characteristic data can serve as an important reference for model correction, help identify factors that may cause prediction deviations under specific working conditions, and improve the stability and credibility of the model. The influence of different prediction model parameters on the prediction results is evaluated through sensitivity analysis, and the key parameters that are most sensitive to the prediction results are identified, thereby optimizing the model structure. The acquisition of parameter sensitivity data can guide the model to adjust key parameters more specifically in the future adaptive update process, avoid blind optimization, and improve the accuracy and convergence of the model. Based on the dynamic predictive control data and sensitivity analysis results, the adaptive update of model parameters ensures that the model can respond to changes in working conditions in real time, allowing the model to continuously adapt to changes in the environment and loads, thereby maintaining a high level of prediction accuracy.The optimized model parameters obtained through adaptive updating can allow the model to be dynamically adjusted to cope with changes in complex loads and environmental factors, ensuring the long-term effectiveness and accuracy of displacement prediction results, and helping to improve the safety and reliability of pile foundation structures during long-term use. The above steps achieve high-precision dynamic prediction of pile foundation displacements through the combination of deep learning and time series analysis, as well as the introduction of attention mechanism and adaptive optimization. This method can effectively capture the impact of load changes on pile foundation structures, provide reliable data support for long-term safety monitoring, risk warning and maintenance optimization, and make the displacement prediction of pile foundation structures in complex environments more accurate, ensuring the long-term stability and safety of the structure.

[0125] Preferably, step S5 comprises the following steps:

[0126] Step S51: constructing a lateral displacement prediction model using optimized model parameters, and performing continuous prediction calculations to obtain an initial displacement prediction sequence;

[0127] The embodiment of the present invention uses the optimized model parameters to construct a lateral displacement prediction model, selects a suitable machine learning algorithm, such as a support vector machine (SVM) or a recursive neural network (RNN), and performs model training based on historical monitoring data (e.g., the displacement data of the pile foundation in the past year). Assume that the historical data contains 1,000 data points, each of which includes environmental factors such as temperature, load, and humidity as input features, and uses an optimized deep neural network as a regression model. Continuous prediction calculations are performed using the optimized parameters, and a time window (such as the next 30 days) is set to gradually predict the displacement of each day, and the results of each prediction are recorded to finally obtain an initial displacement prediction sequence, for example, the predicted displacement value may be [0.2, 0.25, 0.3, 0.28, 0.31, ...] meters.

[0128] Step S52: extracting time series features based on displacement change trend, periodic features and mutation features from the initial displacement prediction data, and verifying the prediction accuracy, thereby obtaining displacement prediction data;

[0129] When the embodiment of the present invention extracts the time series features of the initial data of displacement prediction, it first calculates the displacement change trend, uses a linear regression model to analyze the trend features of the prediction sequence, and obtains the slope of the trend line. For example, if the trend line equation of the displacement sequence is y=0.02x+0.1, it means that the displacement increases by 0.02 meters per time unit. Next, the periodic features are extracted, and the periodic components of the displacement data are analyzed using the fast Fourier transform (FFT). It is assumed that the monthly periodic feature is 0.1 meters. Finally, the mutation features are analyzed, and the quantile regression method is used to detect whether there is an obvious mutation point, such as the displacement suddenly increases to 0.5 meters at a certain point in time. These features are combined to verify the prediction accuracy, and the accuracy of the prediction data is ensured by comparing with the actual observation data, thereby obtaining the processed displacement prediction data.

[0130] Step S53: performing uncertainty quantitative evaluation on the displacement prediction data, thereby obtaining prediction uncertainty data;

[0131] The embodiment of the present invention performs uncertainty quantitative evaluation on displacement prediction data. First, environmental factors related to displacement and their possible range of variation are collected (such as the temperature range of 5 to 35°C and the humidity range of 30% to 90%). A large number of random samples are generated through the Monte Carlo simulation method. Assuming 10,000 simulations, the displacement prediction values ​​under each simulation are calculated to obtain a set of distribution results. Then, the variance and standard deviation of these results are analyzed to quantify the uncertainty and determine the uncertainty range. For example, the standard deviation of the predicted displacement is 0.02 meters. Finally, the prediction uncertainty data is obtained to describe the reliability of the model for future displacement.

[0132] Step S54: calculating the reliability index of the displacement prediction result according to the prediction uncertainty data, thereby obtaining prediction reliability data, wherein the reliability index includes the prediction error distribution, the confidence interval and the prediction accuracy evaluation;

[0133] When calculating the reliability index of the displacement prediction result according to the prediction uncertainty data, the embodiment of the present invention first analyzes the prediction error distribution, calculates the error between the predicted value and the measured value, and performs a normal distribution test, assuming that the mean of the obtained error distribution is 0.01 meters and the standard deviation is 0.02 meters. Next, the confidence interval is calculated based on the prediction error distribution. For example, the confidence interval range of 95% is [0.01-1.96*0.02, 0.01+1.96*0.02], and the obtained confidence interval is [-0.03, 0.05]. Finally, combined with the prediction accuracy evaluation index (such as the root mean square error), these data are summarized as prediction reliability data to comprehensively evaluate the reliability of the prediction results.

[0134] Step S55: Correct the displacement prediction data based on the prediction uncertainty data and the prediction reliability data to obtain corrected prediction result data.

[0135] When the embodiment of the present invention corrects the displacement prediction data based on the prediction uncertainty data and the prediction reliability data, the correction parameters are first set according to the results of the uncertainty analysis. Assume that according to the previous analysis, the correction coefficient is set to 0.8, the initial displacement prediction value is multiplied by the correction coefficient, and the confidence interval of the prediction error is added, so that the corrected displacement = initial displacement × 0.8 + error range. For example, for a certain prediction, the initial value is 0.25 meters, which becomes 0.25 × 0.8 + 0.02 = 0.22 meters after the correction calculation. At this time, the corrected prediction result data obtained after the correction process is a more reliable displacement value, so as to improve the overall prediction accuracy and credibility.

[0136] Based on the model parameters obtained by the previous optimization, the present invention constructs a model that can continuously predict the lateral displacement of the pile foundation. This process integrates the influence of dynamic loads and environmental factors into the model to generate an initial displacement prediction sequence. Through this continuous prediction calculation, the changes in pile foundation displacement can be tracked in real time, providing a basis for subsequent engineering decisions. At the same time, the initial prediction sequence lays the foundation for further feature extraction and accuracy verification. The initial displacement prediction data is analyzed to extract the trend characteristics, periodic characteristics and mutation characteristics of the displacement change, thereby verifying the accuracy of the prediction. The goal of this step is to identify key patterns in the data and confirm the validity of the prediction. The extraction of time series features can provide a deeper understanding of the dynamic behavior of pile foundation displacement, ensuring that the prediction model not only generates data but also provides meaningful trend analysis. In addition, the verification of prediction accuracy improves the credibility of the prediction results and provides a reliable basis for subsequent steps. Through quantitative evaluation, the uncertainty factors that may exist in the prediction data, including model errors, measurement errors and environmental changes, are analyzed to generate prediction uncertainty data. The quantitative evaluation of uncertainty provides a more comprehensive understanding of the prediction results, which can reveal the vulnerability and sensitivity of the model under different working conditions, provide important information for risk assessment and decision-making, and improve the effectiveness of management and response measures. According to the prediction uncertainty data, reliability indicators including prediction error distribution, confidence interval and prediction accuracy evaluation are calculated to generate prediction reliability data. These indicators help identify the stability and credibility of the prediction results. The calculation of reliability indicators can provide quantitative confidence values ​​for the prediction results, so that engineers and decision makers can understand the reliability of the prediction results more clearly, thereby enhancing their trust in the prediction results and facilitating the adoption of more scientific measures in practical applications. Based on the prediction uncertainty data and prediction reliability data, the displacement prediction results are corrected to generate corrected prediction result data. This process ensures that the prediction data can better reflect the actual situation. The correction process makes the final prediction results more accurate and reliable, helps to eliminate potential errors and deviations, and enables engineering personnel to rely on higher quality data support when making decisions and evaluations, thereby improving the safety and sustainability of engineering projects. The entire prediction process not only focuses on the optimization of model parameters and the realization of continuous prediction, but also emphasizes the evaluation and correction of prediction results. Such a process ensures that the pile foundation displacement prediction model has high accuracy and reliability in dynamic and complex environments, can effectively support engineering management and maintenance decisions, and ensure the safety and stability of pile foundation structures. This systematic approach provides strong technical support for the long-term monitoring and management of pile foundation projects.

[0137] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0138] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for constructing a lateral displacement prediction model for pile foundation of a high-pile wharf, characterized in that: The following steps are involved: Step S1: monitor the displacement, stress and load parameters of the pile foundation of the high-pile wharf and generate real-time monitoring parameter data; Identify the working condition of the pile foundation structure through real-time monitoring of parameter data and generate working condition data of the pile foundation structure; Step S2: Perform multi-source load characteristic analysis on the pile foundation structure working condition data, and calculate the load coupling effect to generate load action data; perform soil-pile interaction analysis based on the load action data to generate soil-pile response data; Step S3: evaluating material performance degradation according to soil-pile response data to generate material status data; analyzing the impact of environmental factors based on temperature, humidity and corrosion according to the material status data to generate environmental impact characteristic data; extracting features from real-time monitoring parameter data, and performing dynamic feature fusion based on correlation analysis on environmental correction data to obtain displacement-environment-load correlation characteristic data; Step S4: using the associated feature data to train the deep learning model and obtain the prediction model parameters; performing time series feature analysis on the load action data and the prediction model parameters, and optimizing the prediction accuracy based on the attention mechanism to generate dynamic prediction control data; adaptively updating the prediction model parameters according to the dynamic prediction control data to obtain optimized model parameters; Step S5: Continuously predict the lateral displacement of the pile foundation using the optimized model parameters to generate displacement prediction data; quantify the uncertainty and conduct reliability evaluation on the displacement prediction data to generate corrected prediction result data.

2. The method for constructing a lateral displacement prediction model for pile foundation of a high-pile wharf according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: using multi-source sensors installed on the pile foundation of the high-pile wharf and the soil in the surrounding area to collect sensor parameters in real time, so as to obtain pile foundation displacement data, pile foundation force data and environmental load data, wherein the multi-source sensors include displacement sensors, stress sensors and load sensors; Step S12: pre-processing the pile foundation displacement data, pile foundation force data and environmental load data, and performing unified data dimension processing to obtain real-time monitoring parameter data; Step S13: performing static working condition identification on the real-time monitoring parameter data to obtain static working condition characteristic data, wherein the static working condition identification specifically includes static load working condition classification, structural deformation feature extraction, stress distribution pattern recognition and support condition evaluation; Step S14: performing dynamic response feature extraction, vibration modal analysis, dynamic load feature identification, and dynamic operating condition identification for structural dynamic characteristic evaluation based on the real-time monitoring parameter data, thereby obtaining dynamic operating condition feature data; Step S15: Perform information collaborative fusion processing on the static working condition characteristic data and the dynamic working condition characteristic data, so as to obtain the pile foundation structure working condition data.

3. The method for constructing a lateral displacement prediction model for pile foundation of a high-pile wharf according to claim 2, characterized in that: Step S13 includes the following steps: Step S131: Classifying the environmental load data in the real-time monitoring parameter data based on the loading mode, loading amplitude and loading sequence, and identifying the load condition according to the preset static load condition classification standard, thereby obtaining static load condition classification data; Step S132: extracting deformation characteristics of the pile foundation displacement data, and calculating characteristic quantities of displacement amplitude, deformation trend, deformation rate and deformation mode, thereby obtaining structural deformation characteristic data; Step S133: performing stress distribution pattern recognition based on stress distribution law, stress concentration area, stress transfer path and stress level based on the pile foundation stress data, thereby obtaining stress distribution pattern data; Step S134: evaluating the interaction relationship between the pile foundation and the soil according to the pile foundation displacement data and the pile foundation force data, and generating constraint conditions for the pile end constraint, soil constraint and pile body constraint of the pile foundation, thereby obtaining support condition data; Step S135: feature fusion of static load condition classification data, structural deformation characteristic data, stress distribution pattern data and support condition data to obtain static condition characteristic data.

4. The method for constructing a lateral displacement prediction model for pile foundation of a high-pile wharf according to claim 3, characterized in that: Step S14 includes the following steps: Step S141: extracting dynamic response characteristics of dynamic response parameters of the pile foundation structure based on displacement time history, acceleration response and stress fluctuation based on the real-time monitoring parameter data, thereby obtaining dynamic response characteristic data; Step S142: performing vibration modal analysis according to the dynamic response characteristic data, thereby obtaining vibration modal characteristic data; Step S143: extracting dynamic load characteristics of wave load, wind load and earthquake load from environmental load data, and performing parameter statistics of amplitude, frequency, phase and action direction of dynamic load characteristics, so as to obtain dynamic load characteristic data; Step S144: evaluating dynamic characteristic parameters according to the dynamic response characteristic data and the vibration modal characteristic data to obtain structural dynamic characteristic data, wherein the dynamic characteristic parameters include stiffness characteristics, mass distribution and energy dissipation of the pile foundation structure; Step S145: performing characteristic correlation analysis on the dynamic response characteristic data, the vibration mode characteristic data, the dynamic load characteristic data and the structural dynamic characteristic data, so as to obtain dynamic working condition characteristic data.

5. The method for constructing a lateral displacement prediction model for pile foundation of a high-pile wharf according to claim 4, characterized in that: Step S142 includes the following steps: Step S1421: extracting the natural frequency of the pile foundation structure from the dynamic response characteristic data to obtain natural frequency characteristic data; Step S1422: performing modal vibration shape analysis based on the natural frequency characteristic data, extracting the vibration modal shape of the pile foundation structure, and calculating the amplitude and phase characteristics of each order mode, thereby obtaining modal vibration shape data; Step S1423: Calculating the damping ratio of each mode of the pile foundation structure based on the half-power method for the dynamic response characteristic data and the modal vibration shape data, thereby obtaining damping characteristic data; Step S1424: Analyze the changing rules of the natural frequency characteristic data, the modal vibration shape data and the damping characteristic data based on the time series, and evaluate the time-varying characteristics of the dynamic characteristics of the pile foundation structure, so as to obtain the vibration modal characteristic data.

6. The method for constructing a lateral displacement prediction model for pile foundation of a high-pile wharf according to claim 5, characterized in that: Step S2 includes the following steps: Step S21: extracting multi-source load characteristics from the pile foundation structure working condition data, thereby obtaining multi-source load characteristic data; Step S22: performing load coupling effect analysis based on multi-source load characteristic data, and performing coupling calculation through the mutual influence and superposition effect between environmental loads to generate coupling load data; Step S23: Analyze the temporal and spatial distribution characteristics, effect and change rules of the load action on the multi-source load characteristic data and the coupled load data, so as to obtain the load action data; Step S24: simulating the response of the pile foundation under different load combination conditions according to the coupled load data, extracting the soil-pile interaction characteristics, and generating soil-pile force data, wherein the response simulation under different load combination conditions includes soil resistance, pile deformation, and soil-pile interface contact characteristics; Step S25: generating stress distribution, deformation coordination and constraint conditions between the soil and the pile foundation based on the soil-pile force data and the load action data, thereby obtaining soil-pile interaction characteristic data; Step S26: Perform soil-pile energy dissipation and stress path evolution analysis based on the soil-pile force data and the soil-pile interaction characteristic data, so as to obtain soil-pile response data.

7. The method for constructing a lateral displacement prediction model for pile foundation of a high-pile wharf according to claim 6, characterized in that: Step S3 includes the following steps: Step S31: performing material mechanical property analysis on the soil-pile response data to obtain material performance characteristic data, wherein the material mechanical property analysis includes material strength degradation assessment, elastic modulus variation analysis, plastic deformation feature extraction, and fatigue damage degree calculation; Step S32: evaluating material performance degradation based on the material performance characteristic data and the pre-acquired long-term monitoring data of the environment in which the pile foundation is located, thereby obtaining material status data; Step S33: using environmental monitoring equipment to collect environmental parameters such as temperature, humidity and pH value, thereby obtaining environmental parameter data; Step S34: evaluating the accelerated degradation factor according to the environmental parameter data and the material status data, thereby obtaining environmental impact characteristic data; Step S35: extracting time domain features and frequency domain features from the real-time monitoring parameter data, thereby obtaining multi-dimensional monitoring feature data; Step S36: establishing a displacement-environment-load association model based on the multi-dimensional monitoring characteristic data and the environmental impact characteristic data, and performing feature extraction on the association model to obtain association characteristic data.

8. The method for constructing a lateral displacement prediction model for pile foundation of a high-pile wharf according to claim 7, characterized in that: Step S34 includes the following steps: The accelerated degradation factor is evaluated based on the environmental parameter data and material status data to obtain the environmental impact characteristic data. The accelerated degradation factor is evaluated specifically by the temperature stress coefficient through the Arrhenius formula, the humidity expansion coefficient is evaluated through the Arrhenius humidity-temperature acceleration model, and the corrosion rate coefficient is calculated based on Faraday's law.

9. The method for constructing a lateral displacement prediction model for pile foundation of a high-pile wharf according to claim 8, characterized in that: Step S4 includes the following steps: Step S41: constructing a deep neural network structure based on the associated feature data, and using a back propagation algorithm to perform model training, thereby obtaining prediction model parameters; Step S42: performing time series decomposition on the load action data, and extracting the periodicity characteristics, trend characteristics and random characteristics of the load, so as to obtain a load time series characteristic model; Step S43: performing coupling analysis on the load time series characteristic model and the prediction model parameters to construct a time series correlation prediction model, thereby obtaining time series prediction parameter data; Step S44: optimizing the prediction accuracy based on the attention mechanism according to the time series prediction parameter data, thereby generating dynamic prediction control data; Step S45: performing prediction error analysis on the dynamic prediction control data, calculating the deviation between the predicted value and the measured value, thereby generating prediction error characteristic data; Step S46: performing sensitivity analysis on the prediction model parameters according to the prediction error characteristic data, thereby obtaining parameter sensitivity data; Step S47: Adaptively update the prediction model parameters according to the dynamic prediction control data and the parameter sensitivity data, so as to obtain optimized model parameters.

10. The method for constructing a lateral displacement prediction model for pile foundation of a high-pile wharf according to claim 9, characterized in that: Step S5 includes the following steps: Step S51: constructing a lateral displacement prediction model using optimized model parameters, and performing continuous prediction calculations to obtain an initial displacement prediction sequence; Step S52: extracting time series features based on displacement change trend, periodic features and mutation features from the initial displacement prediction data, and verifying the prediction accuracy, thereby obtaining displacement prediction data; Step S53: performing uncertainty quantitative evaluation on the displacement prediction data, thereby obtaining prediction uncertainty data; Step S54: calculating the reliability index of the displacement prediction result according to the prediction uncertainty data, thereby obtaining prediction reliability data, wherein the reliability index includes the prediction error distribution, the confidence interval and the prediction accuracy evaluation; Step S55: Correct the displacement prediction data based on the prediction uncertainty data and the prediction reliability data to obtain corrected prediction result data.

Images